Here's the BigCodeBench leaderboard with the raw data (elo_mle) and more details about how it's calculated https://
huggingface.co/spaces/bigcode
/bigcodebench-leaderboard
…
CODE
-
BigCodeBench Leaderboard: Code Model Performance Rankings
By
–
-
DeepSeek Coder V2 Matches Best Closed-Source Code Models
By
–
New chart with Code LLMs Based on the BigCodeBench Leaderboard, it shows the impressive performance of DeepSeek Coder V2 (236B, 21B active), which is on par with the best closed-source models. Personally, I've switched to Sonnet and I'm very happy with its code performance.
-
Anthropic Launches Test Case Generation and Prompt Evaluation
By
–
Test case generation and output comparison features are available to all users today. Get started on https://
console.anthropic.com or read more on https://
anthropic.com/news/evaluate-
prompts
…. -
Evaluate Tab Automates Test Case Creation for Prompts
By
–
The new Evaluate tab enables you to automatically create test cases to evaluate your prompt against real-world inputs. Modify your test cases as needed, then run all of them in one click.
-
Anthropic Console Adds Prompt Generation and Side-by-Side Testing
By
–
We've added new features to the Anthropic Console.
— Anthropic (@AnthropicAI) 9 juillet 2024
Claude can generate prompts, create test variables, and show you the outputs of prompts side by side. pic.twitter.com/H6THdoja7ZWe've added new features to the Anthropic Console. Claude can generate prompts, create test variables, and show you the outputs of prompts side by side.
-
Claude 3.5 Creates Crab Game Skin Customization App
By
–
Le he pedido un remix del juego original del cangrejo con el que se anunció Claude 3.5 y me ha creado una app para cambiarle la skin al cangrejo xd
-
Anthropic Enables Artifact Sharing and Remixing in Claude
By
–
Hey cómo mola! Antrophic ahora permitirá a los usuarios publicar sus Artifacts para que cualquier pueda probarlos e incluso remixarlos: pedirle a Claude que te genere variaciones del programa original.
— Carlos Santana (@DotCSV) 9 juillet 2024
Mola! https://t.co/VEuH1IDoBUHey cómo mola! Antrophic ahora permitirá a los usuarios publicar sus Artifacts para que cualquier pueda probarlos e incluso remixarlos: pedirle a Claude que te genere variaciones del programa original. Mola!
-
ElevenLabs TTS API Adds Timestamps for Audio-Text Sync
By
–
@elevenlabs TTS API now includes timestamps for precise text-audio sync. Ideal for subtitles and transcription. How could this improve your projects? #AIAutomation #Transcription
-
Claude Artifacts Now Shareable and Remixable
By
–
Artifacts made with Claude can now be published and shared. You can also remix Artifacts shared by others.
-
Create Cute Snake Game Application
By
–
“Create a functional game of Snake, but make it cuter…” pic.twitter.com/KZrVT4xRhc
— Poe (@poe_platform) 9 juillet 2024“Create a functional game of Snake, but make it cuter…”